Kavya Manohar
Machine Learning Researcher at Adalat AI
Thiruvananthapuram, Kerala, India
Summary
👤
Senior🎓
Top SchoolKavya Manohar is a machine learning researcher and computational linguist with 12 years of experience bridging signal processing, speech technology and language engineering, currently developing ASR for extremely low-resource languages at Adalat AI. She holds a PhD in Speech and Language Processing and led the first quantitative analysis of Malayalam morphological complexity, plus a multifunctional grapheme-to-phoneme system and the Mlphon Python library as open-source contributions. Her work spans practical ASR toolchains (contributions to Kaldi), multilingual G2P (Epitran), and improving accessibility through Malayalam localization for Mozilla Common Voice and OpenType font engineering. Previously an assistant professor, she combines teaching and research strengths to publish in Q1/Q2 SCIE journals and present at international NLP conferences. Based in Thiruvananthapuram, she regularly shares learnings on her blog and focuses on making linguistic resources and tooling available for underrepresented Dravidian languages.
12 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD, Electrical, Electronics and Communications Engineering, Doctor of Philosophy - PhD, Electrical, Electronics and Communications Engineering at APJ Abdul Kalam Technological UniversityM.Tech, Communication Engineering and Siganal Processing, M.Tech, Communication Engineering and Siganal Processing at Government Engineering College, ThrissurB.Tech, Electronics and Communication Engineering, B.Tech, Electronics and Communication Engineering at Government Engineering College, Barton Hill, ThiruvananthapuramAISSCE, Physics, Mathematics, Chemistry, Computer Science, 91%, AISSCE, Physics, Mathematics, Chemistry, Computer Science, 91% at De Paul Public School Thodupuzha
English, Malayalam
Stackoverflow
33reputation
2kreached
0answers
1question
Github Skills (8)
internationalization10
localization10
crowdsourcing8
open-data7
voice6
matlab6
signal-processing6
octave6
Programming languages (10)
Github contributions (5)
common-voice/common-voice
Apr 2019 - Nov 2021
Common Voice is part of Mozilla's initiative to help teach machines how real people speak.
Role in this project:
Localization / Internationalization Specialist
Localization / Internationalization SpecialistContributions:18 commits in 2 years 6 months
Contributions summary:Kavya's commits primarily focus on updating the Malayalam (ml) localization for the Common Voice project. This includes translating and adapting text strings within the `messages.ftl` file, which contains UI text, and `cross-locale.ftl`, which appears to contain cross-language elements. The user's work involves adding new translations, correcting existing ones, and ensuring the accurate representation of the Malayalam language within the project's user interface. The user's contributions directly improve the accessibility and usability of the Common Voice platform for Malayalam speakers.
internet-freedommachinesinitiativeopen-datavoice
kavyamanohar/mlphon
Jan 2017 - Sep 2022
Malayalam phonetic analyser using fst. It is the mirror of https://gitlab.com/smc/mlphon
Contributions:278 commits, 2 PRs, 59 pushes in 5 years 9 months
phoneticmalayalamanalysergitlabfst
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.